public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* libata.force=1.5Gbps doesn't seem to work
@ 2008-06-08 11:35 Nick Craig-Wood
  2008-06-08 15:41 ` Roger Heflin
  0 siblings, 1 reply; 2+ messages in thread
From: Nick Craig-Wood @ 2008-06-08 11:35 UTC (permalink / raw)
  To: linux-kernel

Ever since I changed to AHCI (by fiddling with random options in the
BIOS) my external SATA drive is being run at 3.0 Gbps.  However it
doesn't seem reliable at that - maybe the cable is too long. (It is
probably about 80cm in total - one standard SATA cable going to the
case and another from the case to the drive).

I read in Documentation/kernel-parameters.txt that a command line of

  libata.force=1.5Gbps

Should force all my SATA disks to 1.5 Gbps.

However this doesn't seem to work.

Edited highlights of dmesg - note the selection of 3.0 Gbps for ata6 -
that is what I'm trying to avoid.

[    1.087690] SCSI subsystem initialized
[    1.091690] libata version 3.00 loaded.
[    2.241029] ahci 0000:00:1f.2: version 3.0
[    3.300329] ahci 0000:00:1f.2: AHCI 0001.0200 32 slots 6 ports 3 Gbps 0x3f impl SATA mode
[    3.300366] ahci 0000:00:1f.2: flags: 64bit ncq sntf stag pm led clo pmp pio slum part
[    3.309764] scsi0 : ahci
[    3.309764] scsi1 : ahci
[    3.309764] scsi2 : ahci
[    3.309764] scsi3 : ahci
[    3.309764] scsi4 : ahci
[    3.309764] scsi5 : ahci
[    3.309764] ata1: SATA max UDMA/133 abar m2048@0xfb106000 port 0xfb106100 irq 218
[    3.309764] ata2: SATA max UDMA/133 abar m2048@0xfb106000 port 0xfb106180 irq 218
[    3.309764] ata3: SATA max UDMA/133 abar m2048@0xfb106000 port 0xfb106200 irq 218
[    3.309764] ata4: SATA max UDMA/133 abar m2048@0xfb106000 port 0xfb106280 irq 218
[    3.309764] ata5: SATA max UDMA/133 abar m2048@0xfb106000 port 0xfb106300 irq 218
[    3.309764] ata6: SATA max UDMA/133 abar m2048@0xfb106000 port 0xfb106380 irq 218
[    3.845799] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
[    3.847892] ata1.00: HPA detected: current 586112591, native 586114704
[    3.847926] ata1.00: ATA-7: Maxtor 7L300S0, BANC1E00, max UDMA/133
[    3.847959] ata1.00: 586112591 sectors, multi 0: LBA48 NCQ (not used)
[    3.850048] ata1.00: configured for UDMA/133
[    4.343265] ata2: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
[    4.345363] ata2.00: ATA-7: Maxtor 7B300S0, BANC1B70, max UDMA/133
[    4.345395] ata2.00: 586114704 sectors, multi 0: LBA48 NCQ (not used)
[    4.344422] ata2.00: configured for UDMA/133
[    4.667268] ata3: SATA link down (SStatus 0 SControl 300)
[    4.987268] ata4: SATA link down (SStatus 0 SControl 300)
[    5.307259] ata5: SATA link down (SStatus 0 SControl 300)
[    5.791265] ata6: SATA link up 3.0 Gbps (SStatus 123 SControl 300)    <--- 1.5 Gbps desired here!
[    5.695773] ata6.00: ATA-7: ST3250620NS,     3BKH, max UDMA/133
[    5.695773] ata6.00: 488281250 sectors, multi 0: LBA48 NCQ (depth 31/32)
[    5.827259] ata6.00: configured for UDMA/133
[    5.827259] scsi 0:0:0:0: Direct-Access     ATA      Maxtor 7L300S0   BANC PQ: 0 ANSI: 5
[    5.827259] scsi 1:0:0:0: Direct-Access     ATA      Maxtor 7B300S0   BANC PQ: 0 ANSI: 5
[    5.827259] scsi 5:0:0:0: Direct-Access     ATA      ST3250620NS      n/a  PQ: 0 ANSI: 5
[    6.899647] ahci 0000:04:00.0: AHCI 0001.0000 32 slots 2 ports 3 Gbps 0x3 impl SATA mode
[    6.899684] ahci 0000:04:00.0: flags: 64bit ncq pm led clo pmp pio slum part
[    6.903618] scsi6 : ahci
[    6.903618] scsi7 : ahci
[    6.903618] ata7: SATA max UDMA/133 abar m8192@0xfb000000 port 0xfb000100 irq 19
[    6.903618] ata8: SATA max UDMA/133 abar m8192@0xfb000000 port 0xfb000180 irq 19
[    7.219641] ata7: SATA link down (SStatus 0 SControl 300)
[    7.539656] ata8: SATA link down (SStatus 0 SControl 300)
[    7.777106] sd 0:0:0:0: [sda] Attached SCSI disk
[    7.797106] sd 1:0:0:0: [sdb] Attached SCSI disk
[    7.821107] sd 5:0:0:0: [sdc] Attached SCSI disk

$ cat /proc/cmdline
root=/dev/md0 panic=60 combined_mode=libata libata.atapi_enabled=1 libata.force=1.5Gbps ro

This is with a 2.6.26-rc5 + latest git

$ git-describe
v2.6.26-rc5-159-gaab2545

Thanks in advance for any help!

-- 
Nick Craig-Wood <nick@craig-wood.com> -- http://www.craig-wood.com/nick

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: libata.force=1.5Gbps doesn't seem to work
  2008-06-08 11:35 libata.force=1.5Gbps doesn't seem to work Nick Craig-Wood
@ 2008-06-08 15:41 ` Roger Heflin
  0 siblings, 0 replies; 2+ messages in thread
From: Roger Heflin @ 2008-06-08 15:41 UTC (permalink / raw)
  To: Nick Craig-Wood; +Cc: linux-kernel

Nick Craig-Wood wrote:
> Ever since I changed to AHCI (by fiddling with random options in the
> BIOS) my external SATA drive is being run at 3.0 Gbps.  However it
> doesn't seem reliable at that - maybe the cable is too long. (It is
> probably about 80cm in total - one standard SATA cable going to the
> case and another from the case to the drive).
> 
> I read in Documentation/kernel-parameters.txt that a command line of
> 
>   libata.force=1.5Gbps
> 
> Should force all my SATA disks to 1.5 Gbps.
> 
> However this doesn't seem to work.

I cannot help with the option not working, but you might see if the drives can 
be jumpered to force 1.5Gbps, I know a number of the manufacturers have jumpers 
to force 1.5Gbps since a number of older chipsets (Via sata and probably others) 
don't properly auto-neg 1.5Gbps on a 3.0Gbps drive, and fail to work at all.

                                  Roger

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2008-06-08 15:42 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-06-08 11:35 libata.force=1.5Gbps doesn't seem to work Nick Craig-Wood
2008-06-08 15:41 ` Roger Heflin

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox